Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Jarroslav/agentic-os --skill sdlc-runsgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-runs)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-runs"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-runs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/sdlc-runs"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/sdlc-runs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00198 | $0.03390 |
| Opus 5 | $0.00099 | $0.01695 |
| Sonnet 5 | $0.00040 | $0.00678 |
| Haiku 4.5 | $0.00020 | $0.00339 |
Grade A, and why
sdlc-runs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdlc-runs
What this does
Inspects sdlc-engine heavy-mode runs and, on explicit confirmation, hands off
a resume request to sdlc-engine. It is a stand-in for the legacy sdlc:status
slash command on hosts that only support skills (Codex is the reference example) —
same information, same resume gate, exposed through the skill interface instead
of a command.
This skill never executes or re-runs a pipeline phase itself. It decides what
should resume and why, then delegates the actual execution to sdlc-engine.
Default posture is read-only. The only writes this skill performs on its own are corrective: fixing a stale mutable snapshot to match the append-only event history, and mirroring work-item ledger reconciliation. Anything that restarts pipeline work requires the user to say yes first.
When to invoke
- The user asks for the status of an SDLC run, all runs, or a specific run ID.
- The user wants to resume a run that stopped mid-phase.
- The user is on a host without slash-command support and asks for
sdlc:status. - Another skill or the orchestrator needs a run's current phase/state before deciding whether to dispatch further work.
Guardrails
| Rule | Effect |
|---|---|
| Completed runs are immutable | Never write to a run whose meta.status is completed, under any circumstance. |
| Aborted runs need explicit consent | Never resume a run whose meta.status is aborted without the user answering yes to a direct prompt. |
| Event log is append-only | Never rewrite or truncate events.jsonl. All corrections are additive appends. |
| Log beats snapshot | When meta.json and events.jsonl disagree, treat the event log as ground truth and correct the snapshot — never the other way around. |
| Resume is single-shot | One resume attempt per invocation. A failed resume leaves the run interrupted, not aborted — it stays resumable later. |
Blast-radius shape of this skill's own actions:
| Action | Tag | Notes |
|---|---|---|
| List runs, render catalog, compute status line | R0 | Read-only, no writes. |
Correct meta.json phase fields, append status.repaired / work_item.reconciled, mirror JSONL ledgers, add a Markdown history row |
R1 | Confined to run artifacts under docs/superpowers/runs/ and docs/superpowers/work-items/. |
Hand off a confirmed resume to sdlc-engine |
R2/R3 (downstream) | This skill doesn't perform the repo writes or external side effects itself — it only issues the confirmed handoff. The resumed phase may touch tracked files (R2) or trigger external sync (R3); that's why the resume prompt is a hard gate. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 290 lines · 198 tokens per session scan A 151abe03be63
sdlc-runs is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 198 tokens to every session and 3,390 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.